CN116702588A - Wind power plant key weather factor forecasting method and system based on multi-source data - Google Patents
Wind power plant key weather factor forecasting method and system based on multi-source data Download PDFInfo
- Publication number
- CN116702588A CN116702588A CN202310459786.2A CN202310459786A CN116702588A CN 116702588 A CN116702588 A CN 116702588A CN 202310459786 A CN202310459786 A CN 202310459786A CN 116702588 A CN116702588 A CN 116702588A
- Authority
- CN
- China
- Prior art keywords
- weather
- data
- power plant
- wind power
- meteorological
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013277 forecasting method Methods 0.000 title abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000004044 response Effects 0.000 claims abstract description 21
- 230000035945 sensitivity Effects 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims description 21
- 238000010606 normalization Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 8
- 238000012549 training Methods 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000002459 sustained effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- 238000001363 water suppression through gradient tailored excitation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/02—Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Environmental Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Ecology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Atmospheric Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Computer Hardware Design (AREA)
- Operations Research (AREA)
- Geometry (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
Abstract
The invention discloses a wind farm key meteorological factor forecasting method and system based on multi-source data, and relates to the technical field of intelligent data processing, wherein the method comprises the following steps: connecting a meteorological platform to acquire historical wind farm meteorological factor data, and carrying out multidimensional data source analysis on the historical wind farm meteorological factor data to determine A data sources and B meteorological characteristic elements; b meteorological characteristic elements and A data sources are input into a meteorological characteristic prediction model to obtain wind power plant meteorological characteristic information, a multi-level meteorological factor response interval is identified by combining historical wind power plant meteorological data, a multi-level meteorological factor sensitivity index is generated, and then the key meteorological factors of a target wind power plant are predicted by combining collected meteorological factor prediction data. The method solves the technical problem of low accuracy of the forecasting result caused by single weather forecasting data source of the wind power plant in the prior art, and achieves the technical effect of improving the accuracy of the forecasting result of the key weather factors of the wind power plant.
Description
Technical Field
The invention relates to the technical field of intelligent data processing of wind power plants, in particular to a wind power plant key meteorological factor forecasting method and system based on multi-source data.
Background
In order to mitigate global warming, clean energy has been increasingly called for. Wind energy is an important clean energy source, and is widely developed in many areas of the world, and more large wind farms are built and put into operation. The construction of wind farms is more focused on the influence of unusual weather and meteorological events, so weather forecast of wind farms is more and more important.
The weather forecast data of the wind farm at the current stage is mostly weather forecast data obtained by calculation in a single atmospheric mode or multi-mode integrated forecast data which is not corrected by measured data, has larger deviation from an actual observation result, can only meet the requirement of refinement, and has high accuracy. Therefore, the technical problem of low accuracy of weather forecast results caused by single weather forecast data source of the wind power plant exists in the prior art.
Disclosure of Invention
The application provides a wind power plant key weather factor forecasting method and system based on multi-source data, which are used for solving the technical problem of low accuracy of weather forecasting results caused by single weather forecasting data source in the prior art.
In a first aspect of the application, a method for forecasting key meteorological factors of a wind farm based on multi-source data is provided, and the method comprises the following steps:
Acquiring historical wind farm meteorological data by connecting a meteorological platform;
analyzing the weather data of the historical wind power plant to obtain weather information with high influence on the historical wind power plant;
multidimensional data source analysis is carried out on the weather information with high influence of the historical wind power plant, and A data sources are determined, wherein A is a positive integer greater than 2;
performing feature pairing of a weather feature pairing library based on the A data sources, determining B weather feature elements, inputting the B weather feature elements and the A data sources into a weather law layer in a weather feature prediction model, and outputting weather feature information of a wind power plant, wherein B is a positive integer greater than 1;
identifying a multi-level weather factor response interval based on the historical wind power plant weather data and the wind power plant weather characteristic information, and generating a multi-level weather factor sensitivity index according to an identification result;
and collecting weather factor prediction data, and forecasting weather of the target wind power plant according to the weather factor prediction data and the multi-level weather factor sensitivity index.
In a second aspect of the present application, there is provided a remote intelligent control system for a water gate, the system comprising:
The weather data acquisition module is used for acquiring weather data of the historical wind farm by connecting with a weather platform;
the data analysis module is used for analyzing the weather data of the historical wind power plant and acquiring weather information with high influence on the historical wind power plant;
the multidimensional data source analysis module is used for carrying out multidimensional data source analysis on the weather information with high influence of the historical wind power plant and determining A data sources;
the weather feature information acquisition module is used for carrying out feature pairing of a weather feature pairing library based on the A data sources, determining B weather feature elements, inputting the B weather feature elements and the A data sources into a weather rule layer in a weather feature prediction model, and outputting weather feature information of a wind power plant, wherein B is a positive integer greater than 1;
the multi-level weather factor sensitive index generation module is used for identifying a multi-level weather factor sensitive index based on the historical wind power plant weather data and the wind power plant weather characteristic information and generating a multi-level weather factor sensitive index according to an identification result;
The weather forecast module is used for collecting weather factor forecast data and forecasting weather of the target wind power plant according to the weather factor forecast data and the multi-level weather factor sensitivity index.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the application provides a wind farm key weather factor forecasting method based on multi-source data, relates to the technical field of intelligent data processing, solves the technical problem of low accuracy of weather forecasting results caused by single weather forecasting data source of a wind farm in the prior art, and achieves the technical effects of carrying out weather forecasting on multi-source data of a wind farm and improving accuracy of weather forecasting results.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for forecasting key meteorological factors of a wind farm based on multi-source data, which is provided by the embodiment of the application;
FIG. 2 is a schematic flow chart of determining A data sources in a method for forecasting key meteorological factors of a wind farm based on multi-source data according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of outputting wind farm weather feature information in a wind farm key weather factor forecasting method based on multi-source data according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a wind farm key weather factor forecasting system based on multi-source data according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a meteorological data acquisition module 11, a data analysis module 12, a multi-dimensional data source analysis module 13, a meteorological characteristic information acquisition module 14, a multi-level meteorological factor sensitive index generation module 15 and a meteorological prediction module 16.
Detailed Description
The application provides a wind farm key weather factor forecasting method based on multi-source data, which is used for solving the technical problem of low accuracy of weather forecasting results caused by single weather forecasting data source of a wind farm in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the application provides a wind farm key meteorological factor forecasting method based on multi-source data, which comprises the following steps:
s100: acquiring historical wind farm meteorological data by connecting a meteorological platform;
specifically, the meteorological platform is a meteorological data sharing platform, which collects, analyzes, stores, shares and uses meteorological data information by using an information technology, and can effectively support development of various meteorological services. Wind power refers to wind power generation, a wind power plant is a wind power generation base, and because meteorological types contained in a target wind power plant exist in a certain range, historical wind power plant meteorological data of the target wind power plant are required to be collected, so that the meteorological data existing before the current moment of the target wind power plant are summarized, and the result of summarizing is the historical wind power plant meteorological data, wherein the historical wind power plant meteorological data is provided with time marks and corresponds to the historical wind power plant meteorological data one by one. And logging in a meteorological data sharing platform to search and obtain the meteorological data of the historical wind farm, wherein the meteorological data can be used as basic data for subsequent meteorological analysis.
S200: analyzing the weather data of the historical wind power plant to obtain weather information with high influence on the historical wind power plant;
specifically, the analysis of the weather data of the historical wind farm refers to screening, classifying and sorting the weather data existing in the wind farm before the current moment; the weather with high influence on the wind farm is the weather with influence on the safe operation of the wind farm, such as typhoons, low temperature, ice accumulation, thunderstorms, sand storm and the like; because the construction of the wind power plant is mainly focused on the influence of abnormal weather and meteorological events, the weather information with high influence of the wind power plant is selected to be obtained as basic data of meteorological prediction; and screening weather conditions such as typhoons, low temperature, ice deposition, thunderstorms, sand storm and the like which influence the safe operation of the wind farm from the weather data of the historical wind farm, and obtaining weather data under the current conditions, including images, historical time periods, atmospheric states, air pressure, humidity, temperature, weather distribution and the like, wherein the data are the weather information with high influence of the historical wind farm, and can be used as a basic data source for the subsequent weather analysis.
S300: multidimensional data source analysis is carried out on the weather information with high influence of the historical wind power plant, and A data sources are determined, wherein A is a positive integer greater than 2;
Specifically, multidimensional data source analysis refers to respectively selecting data information with different dimensions to analyze with different dimensions based on the weather information with high influence of the historical wind power plant so as to obtain data sources with different dimensions. For example, based on the weather information with high influence of the historical wind power plant, the real-time image information of the target wind power plant is selected, and the illumination intensity, the visibility, the cloud layer thickness and the like of the current environment can be judged by analyzing the brightness of the real-time image; based on the historical weather information of the high influence of the wind power plant, selecting a period with strong influence of the weather on the wind power plant for analysis, and obtaining the occurrence time point, occurrence frequency, duration and the like of the high influence of the wind power plant; and adding the obtained data sources with different dimensions into the A data sources to obtain the A data sources, wherein A is a positive integer greater than 2.
Further, as shown in fig. 2, step S300 of the embodiment of the present application further includes:
s310: based on the high-influence weather information of the historical wind power plant, extracting an image set of the target wind power plant when the historical wind power plant is high in influence weather by an image acquisition unit, and carrying out real-time image brightness recognition analysis on the image set to obtain a one-dimensional image data source;
S320: based on the weather information with high influence of the historical wind power plant, weather influence analysis is carried out on the weather of the historical period of the target wind power plant, and a two-dimensional period data source is obtained;
s330: detecting and analyzing the historical atmosphere detection of the target wind power plant based on the weather information with high influence of the historical wind power plant to obtain a three-dimensional atmosphere detection data source;
s340: performing numerical analysis on the historical weather values of the target wind power plant based on the weather information with high influence of the historical wind power plant to obtain a four-dimensional numerical data source;
s350: the one-dimensional image data source, the two-dimensional period data source, the three-dimensional atmospheric sounding data source, the four-dimensional numerical data source are added to the a data sources.
Specifically, based on the obtained high-influence weather information of the historical wind power plant, the collection of all picture data in the high-influence weather information of the historical wind power plant is extracted, and the illumination intensity, cloud layer thickness and the like of the current environment can be judged by analyzing the brightness of the real-time image, wherein the data are one-dimensional image data sources; based on the obtained weather information with high influence on the historical wind power plant, selecting a period with strong influence of weather on the wind power plant for analysis, and obtaining the occurrence time point, occurrence frequency, duration and the like of the weather with high influence on the wind power plant, wherein the data are two-dimensional period data sources; based on the obtained weather information with high influence on the historical wind power plant, selecting a historical atmosphere detection collection of the target wind power plant, wherein the historical atmosphere detection collection comprises ground meteorological observation, high-altitude meteorological observation, atmosphere remote sensing detection, meteorological satellite detection and the like for analysis, and the atmospheric state and the change thereof from the ground to the high altitude and from the local part to the whole wind power plant can be obtained, and the data are three-dimensional atmosphere detection data sources; based on the obtained weather information with high influence on the historical wind power plant, the historical weather values of the target wind power plant are selected for analysis, and the air pressure values, the humidity values, the temperature values, the dew point temperature values and the like in the wind power plant can be obtained, wherein the data are four-dimensional digital data sources; all the examples of the four types of data sources jointly form A data sources, wherein A is a positive integer greater than 2.
S400: performing feature pairing of a weather feature pairing library based on the A data sources, determining B weather feature elements, inputting the B weather feature elements and the A data sources into a weather law layer in a weather feature prediction model, and outputting weather feature information of a wind power plant, wherein B is a positive integer greater than 1;
specifically, the weather feature pairing library is a feature set formed by integrating all weather features, such as air pressure, temperature, humidity, wind speed and the like, and is used as a reference set of weather feature pairing. All the examples of the one-dimensional image data source, the two-dimensional time period data source, the three-dimensional atmosphere detection data source and the four-dimensional numerical data source are subjected to feature pairing with the weather feature pairing library one by one, so that B weather feature elements can be obtained, wherein B is a positive integer greater than 1; the meteorological characteristic prediction model is a neural network model which can be continuously subjected to self-iterative optimization in machine learning. And inputting the B weather characteristic elements and the A data sources into a weather law layer in a weather characteristic prediction model, and outputting weather characteristic information of the wind power plant, wherein the weather characteristic information can be used as reference data for subsequently carrying out multi-level weather factor response interval identification.
Further, step S400 of the embodiment of the present application further includes:
s410: pairing the image meteorological features in the meteorological feature pairing library by the one-dimensional image data source to obtain image brightness meteorological feature elements;
s420: pairing the two-dimensional time period data source with time period weather features in the weather feature pairing library to obtain time period influence weather feature elements;
s430: pairing the atmospheric state meteorological features in the meteorological feature pairing library by the three-dimensional atmospheric detection data source to obtain atmospheric state meteorological feature elements;
s440: pairing weather numerical value weather characteristics in the weather characteristic pairing library by using the four-dimensional numerical value data source to obtain weather numerical value weather characteristic elements;
s450: and adding the image brightness weather feature element, the period influencing weather feature element, the atmosphere state weather feature element and the weather value weather feature element to the B weather feature elements.
Specifically, the one-dimensional image data sources are paired with the weather feature pairing library one by one, and the image data sources with the same weather features are calculated as an image brightness weather feature element to obtain an image brightness weather feature element set; pairing the two-dimensional time period data sources with the weather feature pairing library one by one, and calculating the time period data sources with the same weather features as time period data weather feature elements to obtain a time period influence weather feature element set; pairing the three-dimensional atmospheric detection data sources with the meteorological feature pairing library one by one, and calculating the atmospheric detection data sources with the same meteorological features as an atmospheric detection meteorological feature element to obtain an atmospheric state meteorological feature element set; pairing the four-dimensional numerical data sources with the weather feature pairing library one by one, and calculating the four-dimensional numerical data sources with the same weather feature as an atmosphere detection weather feature element to obtain a weather numerical weather feature element set; b weather characteristic elements are formed by the image brightness weather characteristic element set, the period influence weather characteristic element set, the atmosphere state weather characteristic element set and the weather value weather characteristic element set, and can be used as basic data for subsequently outputting weather characteristic information of a wind power plant.
Further, step S400 of the embodiment of the present application further includes:
s411: assigning a first weight to the image brightness weather feature element;
s421: assigning a second weight to the period of time-affecting weather-feature element;
s431: a third weight is distributed to the atmospheric state weather feature element;
s441: assigning a fourth weight to the weather value weather characteristic element;
s451: and integrating the first weight, the second weight, the third weight and the fourth weight, and updating the B weather feature elements according to different weight proportions.
Specifically, according to the accuracy degree of weather prediction by the four types of characteristic elements, respectively carrying out weight distribution on the image brightness weather characteristic elements, the time period influence weather characteristic elements, the atmosphere state weather characteristic elements and the weather value weather characteristic elements; the weight proportion of each type of characteristic element is in direct proportion to the accuracy of weather prediction, for example, the accuracy degree of weather prediction is carried out on weather according to the image brightness weather characteristic element, the weight distribution coefficient is 1, and the weight proportion of the corresponding four types of characteristic elements is 1:2:4:3; the first weight is distributed to the image brightness weather feature elements, the second weight is distributed to the period-affected weather feature elements, the third weight is distributed to the atmosphere state weather feature elements, and the fourth weight is distributed to the weather value weather feature elements; and integrating the first weight, the second weight, the third weight and the fourth weight, and updating the B weather feature elements according to different weight proportions, so that the accuracy of the B weather feature elements can be improved, and the accuracy of outputting weather feature information of the wind power plant is further improved.
Further, as shown in fig. 3, step S400 of the embodiment of the present application further includes:
s460: acquiring weather source characteristic data of the target wind power plant according to the B weather characteristic elements with the weights and the A data sources;
s470: according to the weather source characteristic data of the target wind power plant, air pressure source data, humidity source data, temperature source data and wind speed source data are obtained;
s480: inputting the air pressure source data, the humidity source data, the temperature source data and the wind speed source data into a weather law layer of the weather characteristic prediction model to generate air pressure law characteristic data, humidity law characteristic data, temperature law characteristic data and wind speed law characteristic data;
s490: and carrying out normalization processing on the air pressure rule characteristic data, the humidity rule characteristic data, the temperature rule characteristic data and the wind speed rule characteristic data, and outputting meteorological characteristic information of the wind power plant.
Specifically, the weather source characteristic data of the target wind power plant, namely weather characteristics contained in each data source, comprise air pressure, temperature, humidity and the like; extracting target wind farm weather source characteristic data from the B weather characteristic elements with the weights and the A data sources, and obtaining air pressure source data, humidity source data, temperature source data and wind speed source data from the target wind farm weather source characteristic data;
The weather feature prediction model is a neural network model in machine learning, which can be continuously subjected to self iterative optimization, and can be obtained through a training data set and a supervision data set, wherein each group of training data in the training data set comprises air pressure source data, humidity source data, temperature source data and wind speed source data, and the supervision data set is weather rule supervision data which has a corresponding relation with the training data set; the process of constructing the weather feature prediction model may be that each set of training data in the training data set is firstly input into the weather feature prediction model, then output supervision adjustment of the weather feature prediction model is performed through supervision data corresponding to the set of training data, if the output result of the weather feature prediction model is consistent with the supervision data, the current set of training is finished, and further, all data in the training data set is trained until training of all training data is completed, thereby completing training of the weather feature prediction model. In order to ensure the accuracy of the weather feature prediction model, the weather feature prediction model can be tested through a test data set, the test accuracy can be set to be 85%, and if the test accuracy of the current test data set meets 85%, the construction of the weather feature prediction model is completed;
And finally, inputting the air pressure source data, the humidity source data, the temperature source data and the wind speed source data into a weather law layer of the weather characteristic prediction model, and outputting air pressure law characteristic data, humidity law characteristic data, temperature law characteristic data and wind speed law characteristic data.
Specifically, normalization is to map all data into the same scale by a mathematical function. Because the obtained data are irregular in size, singular sample data exist, large-number calculation exists in the singular sample data, the calculation is very time-consuming, the calculation result is abnormally large, in addition, the weight distribution is uneven, the weight obtained by the large number is possibly larger, but the prediction result is inaccurate because the large number is not necessarily the most critical factor for determining the data result; the purpose of the normalization is to limit the pre-processed data to a range, such as [0,1] or [ -1,1], to eliminate the adverse effects caused by the singular sample data. And carrying out normalization processing on the air pressure rule characteristic data, the humidity rule characteristic data, the temperature rule characteristic data and the wind speed rule characteristic data, and outputting wind power plant weather characteristic information, wherein the wind power plant weather characteristic information can be used as basic data for identifying multi-level weather factor response intervals.
S500: identifying a multi-level weather factor response interval based on the historical wind power plant weather data and the wind power plant weather characteristic information, and generating a multi-level weather factor sensitivity index according to an identification result;
specifically, the historical wind farm meteorological data and the wind farm meteorological characteristic information are used as basic data, multi-level meteorological factor response intervals are identified, the multi-level meteorological factor response intervals are emergency response intervals divided according to the influence degree, development situation and possible damage of weather, the multi-level meteorological factor response intervals are identified, the historical meteorological data of the target wind farm can be divided, multi-level meteorological factor sensitivity indexes can be generated according to identification results, and the multi-level meteorological factor sensitivity indexes can be used as reference standards for subsequent weather prediction.
Further, step S500 of the embodiment of the present application further includes:
s510: acquiring wind and rain information of the historical wind farm according to the weather data of the historical wind farm, and acquiring a result of acquiring the wind and rain information of the historical wind farm;
s520: analyzing and obtaining weather and meteorological influence grade data based on the historical weather and meteorological information acquisition result;
S530: according to the weather and meteorological influence grade data, weather and meteorological characteristic information of the wind power plant is adjusted, and a weather and meteorological characteristic adjustment result is obtained;
s540: and identifying the multi-level weather factor response interval according to the weather and weather characteristic adjustment result, and generating a multi-level weather factor sensitivity index according to the identification result.
Specifically, the wind and rain information of the historical wind farm refers to the data information of the wind and rain weather of the target wind farm in a period of time, and the wind and rain information of the historical wind farm is collected based on the weather data of the historical wind farm, and the weather data of the wind and rain weather are screened out to form a historical wind and rain information collection result; analyzing the historical wind and rain information acquisition result, namely grading all wind and rain information according to wind power grade, rainfall, duration time, influence degree on the running condition of the wind power plant and the like, and obtaining wind and rain weather influence grade data; and adjusting the weather characteristic information of the wind power plant according to the weather and meteorological influence level data, namely sorting and sorting the weather characteristic information according to the weather and meteorological influence level data to obtain a weather and meteorological characteristic adjustment result.
Specifically, the multi-level weather factor response interval refers to an emergency response interval divided according to the influence degree, development situation and possible damage of weather, for example, a storm warning signal is divided into four levels, which are respectively represented by blue, yellow, orange and red, and each level represents a rainfall interval. Storm blue warning signal: the rainfall will be more than 50 mm, or more than 50 mm, within 12 hours, may or may have been affected and rainfall may be sustained; storm yellow warning signal: the rainfall will be more than 50 mm, or more than 50 mm, within 6 hours, and may or may not be affected and rainfall may continue; storm orange warning signal: the rainfall will be more than 50 mm in 3 hours, or more than 50 mm, possibly or already causing a large impact and rainfall may be sustained; storm red warning signal: the amount of rainfall will be more than 100 mm in 3 hours, or more than 100 mm, may or may not have serious impact and rainfall may continue. And identifying the weather and weather characteristic adjustment results and weather factor response intervals one by one, determining in which interval each weather characteristic is, and finally generating a multi-level weather factor sensitivity index according to the identification result, wherein if a storm warning signal is classified into four levels according to rainfall, duration and influence degree, the multi-level weather factor sensitivity index can be classified according to the sizes of all influence factors from high to low, and the multi-level weather factor sensitivity index can be used as a reference standard for subsequent weather forecast.
S600, weather factor prediction data are collected, and weather of the target wind power plant is predicted according to the weather factor prediction data and the multi-level weather factor sensitivity index.
Specifically, current meteorological data of a target wind power plant are collected, and the data are processed by considering the mutual influence among all meteorological factors to generate meteorological factor prediction data; and forecasting weather of the target wind power plant by combining the weather factor forecast data and the multi-level weather factor sensitivity index, so that the accuracy of the forecast data can be improved.
Further, step S600 of the embodiment of the present application further includes:
s610: acquiring wind data, rain data and temperature data of a target wind power plant through a sensing unit;
s620: and carrying out linear correlation on the wind data, the rain data and the temperature data to obtain a linear correlation result, wherein a linear correlation formula is as follows:
wherein, D (X) >0, D (Y) >0, D (Z) >0, X is wind data, Y is rain data, and Z is temperature data.
S630: and generating weather factor prediction data based on the linear correlation result.
Specifically, the sensing unit is weather monitoring equipment, which can continuously monitor weather environmental data such as environmental temperature, relative humidity, wind speed, wind direction, atmospheric pressure, rainfall, photoelectric radiation, PM2.5, PM10 and the like for 24 hours, and analyze and sort the monitored data to transmit the data to people at one time; acquiring wind data, rain data and temperature data of a target wind power plant through a sensing unit; wind data, rain data and temperature data refer to data affecting weather in a wind farm, and include wind speed, wind direction, storm, high temperature, low temperature and the like; wind data, rain data and temperature data are linearly related, wind speed influences rain drifting, temperature influences rain and snow changing and the like; linear correlation means that a functional relationship exists among several variables, and one variable change can affect other variables; performing linear correlation on the wind data, the rain data and the temperature data to obtain a linear correlation result, namely a functional relation expression formula among the wind data, the rain data and the temperature data:
Wherein, D (X) >0, D (Y) >0, D (Z) >0, X is wind data, Y is rain data, and Z is temperature data. According to the linear correlation formula, wind data, rain data and temperature data are calculated and adjusted, so that more accurate weather factor prediction data can be obtained.
In summary, the embodiment of the application has at least the following technical effects:
according to the method, historical wind farm meteorological data are obtained through connection with a meteorological platform; analyzing the weather data of the historical wind power plant to obtain weather information with high influence on the historical wind power plant; further, multidimensional data source analysis is carried out on the weather information with high influence of the historical wind power plant, and A data sources are determined; performing feature pairing of a weather feature pairing library based on the A data sources to determine B weather feature elements; inputting the B weather characteristic elements and the A data sources into a weather law layer in a weather characteristic prediction model to obtain weather characteristic information of the wind power plant; then, based on the historical wind power plant meteorological data and the wind power plant meteorological characteristic information, identifying a multi-level meteorological factor response interval, and generating a multi-level meteorological factor sensitivity index according to an identification result; and finally, collecting weather factor prediction data, and forecasting weather of the target wind power plant according to the weather factor prediction data and the multi-level weather factor sensitivity index.
The technical effect of carrying out weather forecast of multi-source data on the wind farm and improving accuracy of weather forecast results is achieved.
Example two
Based on the same inventive concept as the wind farm key weather factor forecasting method based on multi-source data in the foregoing embodiments, as shown in fig. 4, the present application provides a wind farm key weather factor forecasting system based on multi-source data, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
the weather data acquisition module 11 is used for acquiring weather data of the historical wind farm by connecting a weather platform;
the data analysis module 12 is used for analyzing the weather data of the historical wind power plant and acquiring weather information with high influence of the historical wind power plant;
the multidimensional data source analysis module 13 is used for carrying out multidimensional data source analysis on the weather information with high influence of the historical wind power plant, and determining A data sources;
the weather feature information acquisition module 14 is configured to perform feature pairing of a weather feature pairing library based on the a data sources, determine B weather feature elements, input the B weather feature elements and the a data sources into a weather law layer in a weather feature prediction model, and output weather feature information of a wind farm, where B is a positive integer greater than 1;
The multi-level weather factor sensitive index generation module 15 is used for identifying a multi-level weather factor response interval based on the historical wind power plant weather data and the wind power plant weather characteristic information, and generating a multi-level weather factor sensitive index according to an identification result;
the weather forecast module 16 is configured to collect weather factor forecast data, and forecast weather of the target wind farm according to the weather factor forecast data and the multi-level weather factor sensitivity index.
Further, the system further comprises:
the image brightness recognition analysis module is used for extracting an image set of the target wind power plant when the historical wind power plant highly influences weather based on the historical wind power plant highly influences weather information, and carrying out real-time image brightness recognition analysis on the image set to obtain a one-dimensional image data source;
the weather effect analysis module is used for carrying out weather effect analysis on the weather of the historical period of the target wind power plant based on the high-influence weather information of the historical wind power plant to obtain a two-dimensional period data source;
The atmosphere detection analysis module is used for carrying out detection analysis on the historical atmosphere detection of the target wind power plant based on the weather information with high influence of the historical wind power plant to obtain a three-dimensional atmosphere detection data source;
the numerical analysis module is used for carrying out numerical analysis on the historical weather values of the target wind power plant based on the weather information with high influence of the historical wind power plant to obtain a four-dimensional numerical data source;
further, the system further comprises:
the image brightness weather feature pairing module is used for pairing the image weather features of the one-dimensional image data source in the weather feature pairing library to obtain image brightness weather feature elements;
the time period influence weather feature pairing module is used for pairing the time period weather features in the weather feature pairing library by the two-dimensional time period data source to obtain time period influence weather feature elements;
the atmospheric state weather feature pairing module is used for carrying out atmospheric state weather feature pairing on the three-dimensional atmospheric detection data source in the weather feature pairing library to obtain atmospheric state weather feature elements;
The weather value weather characteristic pairing module is used for pairing weather value weather characteristics in the weather characteristic pairing library by the four-dimensional value data source to obtain weather value weather characteristic elements;
further, the system further comprises:
the weight distribution module is used for distributing first weights to the image brightness weather characteristic elements; assigning a second weight to the period of time-affecting weather-feature element; a third weight is distributed to the atmospheric state weather feature element; assigning a fourth weight to the weather value weather characteristic element;
further, the system further comprises:
the weather source characteristic data acquisition module is used for acquiring weather source characteristic data of the target wind power plant according to the B weather characteristic elements with the weights and the A data sources;
the weather characteristic prediction model module is used for inputting the air pressure source data, the humidity source data, the temperature source data and the wind speed source data into a weather rule layer of the weather characteristic prediction model to generate air pressure rule characteristic data, humidity rule characteristic data, temperature rule characteristic data and wind speed rule characteristic data;
The normalization processing module is used for carrying out normalization processing on the air pressure rule characteristic data, the humidity rule characteristic data, the temperature rule characteristic data and the wind speed rule characteristic data and outputting weather characteristic information of the wind power plant;
further, the system further comprises:
the historical wind power plant weather information acquisition module is used for acquiring historical wind power plant weather information according to the historical wind power plant weather data to obtain a historical wind power plant weather information acquisition result;
the result analysis module is used for analyzing and obtaining weather and weather influence grade data based on the historical weather and weather information acquisition result;
the weather characteristic adjustment module is used for adjusting weather characteristic information of the wind power plant according to the weather influence grade data to obtain weather characteristic adjustment results;
the weather factor response interval identification module is used for identifying the multi-level weather factor response interval for the weather characteristic adjustment result and generating a multi-level weather factor sensitivity index according to the identification result;
Further, the system further comprises:
the wind power plant data acquisition module is used for acquiring wind data, rain data and temperature data of a target wind power plant through the sensing unit;
the linear correlation module is used for carrying out linear correlation on the wind data, the rain data and the temperature data to obtain a linear correlation result, and a linear correlation formula is as follows:
wherein, D (X) >0, D (Y) >0, D (Z) >0, X is wind data, Y is rain data, Z is temperature data;
and the weather factor prediction data generation module is used for generating weather factor prediction data based on the linear correlation result.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. The method is applied to a wind power plant key weather factor forecasting system based on multi-source data, and the wind power plant key weather factor forecasting system based on the multi-source data comprises an image acquisition unit and a sensing unit, and the method comprises the following steps:
acquiring historical wind farm meteorological factor data by connecting a meteorological platform;
analyzing the weather factor data of the historical wind power plant to obtain weather information with high influence on the historical wind power plant;
Multidimensional data source analysis is carried out on the weather information with high influence of the historical wind power plant, and A data sources are determined, wherein A is a positive integer greater than 2;
performing feature pairing of a weather feature pairing library based on the A data sources, determining B weather feature elements, inputting the B weather feature elements and the A data sources into a weather law layer in a weather feature prediction model, and outputting weather feature information of a wind power plant, wherein B is a positive integer greater than 1;
identifying a multi-level weather factor response interval based on the historical wind power plant weather data and the wind power plant weather characteristic information, and generating a multi-level weather factor sensitivity index according to an identification result;
and collecting meteorological factor prediction data, and forecasting the key meteorological factors of the target wind power plant according to the meteorological factor prediction data and the multi-level meteorological factor sensitivity index.
2. The method of claim 1, wherein a data sources are determined, the method further comprising:
based on the high-influence weather information of the historical wind power plant, extracting an image set of the target wind power plant when the historical wind power plant is high in influence weather by an image acquisition unit, and carrying out real-time image brightness recognition analysis on the image set to obtain a one-dimensional image data source;
Based on the weather information with high influence of the historical wind power plant, weather influence analysis is carried out on the weather of the historical period of the target wind power plant, and a two-dimensional period data source is obtained;
detecting and analyzing the historical atmosphere detection of the target wind power plant based on the weather information with high influence of the historical wind power plant to obtain a three-dimensional atmosphere detection data source;
performing numerical analysis on the historical weather values of the target wind power plant based on the weather information with high influence of the historical wind power plant to obtain a four-dimensional numerical data source;
the one-dimensional image data source, the two-dimensional period data source, the three-dimensional atmospheric sounding data source, the four-dimensional numerical data source are added to the a data sources.
3. The method of claim 1, wherein B weather feature elements are determined, the method further comprising:
pairing the image meteorological features in the meteorological feature pairing library by the one-dimensional image data source to obtain image brightness meteorological feature elements;
pairing the two-dimensional time period data source with time period weather features in the weather feature pairing library to obtain time period influence weather feature elements;
pairing the atmospheric state meteorological features in the meteorological feature pairing library by the three-dimensional atmospheric detection data source to obtain atmospheric state meteorological feature elements;
Pairing weather numerical value weather characteristics in the weather characteristic pairing library by using the four-dimensional numerical value data source to obtain weather numerical value weather characteristic elements;
and adding the image brightness weather feature element, the period influencing weather feature element, the atmosphere state weather feature element and the weather value weather feature element to the B weather feature elements.
4. The method of claim 3, wherein B weather feature elements are determined, the method further comprising:
assigning a first weight to the image brightness weather feature element;
assigning a second weight to the period of time-affecting weather-feature element;
a third weight is distributed to the atmospheric state weather feature element;
assigning a fourth weight to the weather value weather characteristic element;
and integrating the first weight, the second weight, the third weight and the fourth weight, and updating the B weather feature elements according to different weight proportions.
5. The method of claim 1, outputting wind farm weather trait information, the method further comprising:
acquiring weather source characteristic data of the target wind power plant according to the B weather characteristic elements with the weights and the A data sources;
According to the weather source characteristic data of the target wind power plant, air pressure source data, humidity source data, temperature source data and wind speed source data are obtained;
inputting the air pressure source data, the humidity source data, the temperature source data and the wind speed source data into a weather law layer of the weather characteristic prediction model to generate air pressure law characteristic data, humidity law characteristic data, temperature law characteristic data and wind speed law characteristic data;
and carrying out normalization processing on the air pressure rule characteristic data, the humidity rule characteristic data, the temperature rule characteristic data and the wind speed rule characteristic data, and outputting meteorological characteristic information of the wind power plant.
6. The method of claim 1, wherein the identification of the multi-level weather factor response interval is performed, the method further comprising:
acquiring wind and rain information of the historical wind farm according to the weather data of the historical wind farm, and acquiring a result of acquiring the wind and rain information of the historical wind farm;
analyzing and obtaining weather and meteorological influence grade data based on the historical weather and meteorological information acquisition result;
according to the weather and meteorological influence grade data, weather and meteorological characteristic information of the wind power plant is adjusted, and a weather and meteorological characteristic adjustment result is obtained;
And identifying the multi-level weather factor response interval according to the weather and weather characteristic adjustment result, and generating a multi-level weather factor sensitivity index according to the identification result.
7. The method of claim 1, wherein meteorological factor prediction data is collected, the method further comprising:
acquiring wind data, rain data and temperature data of a target wind power plant through a sensing unit;
and carrying out linear correlation on the wind data, the rain data and the temperature data to obtain a linear correlation result, wherein a linear correlation formula is as follows:
wherein, D (X) >0, D (Y) >0, D (Z) >0, X is wind data, Y is rain data, and Z is temperature data.
S630 generates weather factor prediction data based on the linear correlation result.
8. A wind farm critical weather factor forecasting system based on multi-source data, the system comprising:
the weather data acquisition module is used for acquiring weather factor data of the historical wind power plant through connecting a weather platform;
the data analysis module is used for analyzing the weather factor data of the historical wind power plant and acquiring weather information with high influence on the historical wind power plant;
The multidimensional data source analysis module is used for carrying out multidimensional data source analysis on the weather information with high influence of the historical wind power plant and determining A data sources;
the weather feature information acquisition module is used for carrying out feature pairing of a weather feature pairing library based on the A data sources, determining B weather feature elements, inputting the B weather feature elements and the A data sources into a weather rule layer in a weather feature prediction model, and outputting weather feature information of a wind power plant, wherein B is a positive integer greater than 1;
the multi-level weather factor sensitive index generation module is used for identifying a multi-level weather factor response interval based on the historical wind power plant weather data and the wind power plant weather characteristic information and generating a multi-level weather factor sensitive index according to an identification result;
the weather forecast module is used for collecting weather factor forecast data and forecasting key weather factors of the target wind power plant according to the weather factor forecast data and the multi-level weather factor sensitivity index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310459786.2A CN116702588A (en) | 2023-04-25 | 2023-04-25 | Wind power plant key weather factor forecasting method and system based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310459786.2A CN116702588A (en) | 2023-04-25 | 2023-04-25 | Wind power plant key weather factor forecasting method and system based on multi-source data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116702588A true CN116702588A (en) | 2023-09-05 |
Family
ID=87828265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310459786.2A Pending CN116702588A (en) | 2023-04-25 | 2023-04-25 | Wind power plant key weather factor forecasting method and system based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116702588A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117270079A (en) * | 2023-10-17 | 2023-12-22 | 珠海光焱科技有限公司 | Meteorological monitoring system and method based on multi-source data fusion |
-
2023
- 2023-04-25 CN CN202310459786.2A patent/CN116702588A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117270079A (en) * | 2023-10-17 | 2023-12-22 | 珠海光焱科技有限公司 | Meteorological monitoring system and method based on multi-source data fusion |
| CN117270079B (en) * | 2023-10-17 | 2024-03-12 | 珠海光恒科技有限公司 | Meteorological monitoring system and method based on multi-source data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112233091B (en) | Wind turbine blade image damage detection and positioning method | |
| CN112308292B (en) | Method for drawing fire risk grade distribution map | |
| CN111623722B (en) | Multi-sensor-based slope deformation three-dimensional monitoring system and method | |
| CN114168906B (en) | Mapping geographic information data acquisition system based on cloud computing | |
| CN109407177B (en) | Machine learning and conventional meteorological observation-based fog identification system and application method | |
| CN108896021B (en) | Method for extracting artificial forest stand structure parameters based on aerial photogrammetry point cloud | |
| WO2020111934A1 (en) | A method and system for detection of natural disaster occurrence | |
| CN110888186A (en) | Method for forecasting hail and short-time heavy rainfall based on GBDT + LR model | |
| CN116702588A (en) | Wind power plant key weather factor forecasting method and system based on multi-source data | |
| CN116308958A (en) | Carbon emission online detection and early warning system and method based on mobile terminal | |
| CN117538503A (en) | Real-time intelligent soil pollution monitoring system and method | |
| CN109543911B (en) | Sunlight radiation prediction method and system | |
| KR102591379B1 (en) | Method of Calculating Real Time Visibility using Random Forest Machine Learning and Data of Weather Observations and Model Predictions | |
| CN114417981A (en) | Intelligent river length patrol system | |
| CN113935228A (en) | L-band rough sea surface radiation brightness and temperature simulation method based on machine learning | |
| Sharma et al. | A Weather Forecasting System using concept of Soft Computing: A new approach | |
| CN113176420A (en) | Wind speed forecasting and correcting system for power grid tower point | |
| CN108614803A (en) | A kind of meteorological data method of quality control and system | |
| CN115421220A (en) | Multi-factor local precipitation indication method and system based on deep learning | |
| CN114283344A (en) | Automatic real-time monitoring method and system for forest ecological hydrological process | |
| Nakagawa et al. | Application of random forest to classify weather observation into rainfall using GNSS receiver | |
| Tahsin et al. | Comparative analysis of weather prediction using ensemble learning models and neural network | |
| CN117571056B (en) | Environment protection monitoring method and system based on Internet of things | |
| CN117849907B (en) | Meteorological disaster targeted early warning method and system based on multi-source data | |
| CN117607019B (en) | Intelligent detection method and detection system for electric power fitting surface |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |